Security audit
Security checks for vulnerabilities and agentic risk
This skill analyzes public website structure and saves local reports, with some usability cautions but no evidence of deception, exfiltration, or unsafe privileged behavior.
Install this if you want a Chinese-language website analysis workflow. Before using it on private, authenticated, or proprietary sites, confirm whether you want reports and screenshots saved locally in the workspace, and provide a specific target URL to avoid accidental broad browsing.
The trigger phrases are broad enough that the skill may activate for generic requests about websites, structure, or functionality rather than only for clear, user-intended site analysis tasks. Over-broad activation can cause unintended browsing, content extraction, and downstream file creation, which expands data exposure and may invoke the skill in contexts the user did not mean.
The skill instructions and output template are entirely in Chinese, implying a fixed language mode without offering the user a choice of language or locale. This can violate language/locale policy when no opt-in or justification is provided.
The skill instructs the agent to save reports and screenshots to the workspace without explicitly informing the user or requiring consent. Undisclosed persistence can surprise users, retain sensitive extracted website data locally, and create privacy or policy issues if the analyzed content includes proprietary or regulated information.
This markdown file presents the analysis guide entirely in Chinese, including all section headings and criteria, with no indication that language selection is optional or that the skill is intentionally region-specific. Per the policy, forcing a specific language without user opt-in is a natural-language policy violation.
No suspicious patterns detected.
